Skip to content

Multiply lr scheduler steps by num_processes. #3983

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 13, 2023

Conversation

eliphatfs
Copy link
Contributor

What does this PR do?

Fixes #3954.

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@sayakpaul @muellerzr

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Jul 7, 2023

The documentation is not available anymore as the PR was closed or merged.

Copy link
Member

@sayakpaul sayakpaul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks much!

@eliphatfs
Copy link
Contributor Author

Is this supposed to be merged now?

@sayakpaul
Copy link
Member

Oh I was waiting for @muellerzr's eyes on this too.

@eliphatfs
Copy link
Contributor Author

Please do not merge yet. It seems that we should not multiply the steps by accumulation.

@sayakpaul sayakpaul requested a review from muellerzr July 13, 2023 12:11
Copy link
Contributor

@muellerzr muellerzr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

@sayakpaul sayakpaul merged commit ece5522 into huggingface:main Jul 13, 2023
orpatashnik pushed a commit to orpatashnik/diffusers that referenced this pull request Aug 1, 2023
* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.
orpatashnik pushed a commit to orpatashnik/diffusers that referenced this pull request Aug 1, 2023
* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.
orpatashnik pushed a commit to orpatashnik/diffusers that referenced this pull request Aug 1, 2023
* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.
AmericanPresidentJimmyCarter pushed a commit to AmericanPresidentJimmyCarter/diffusers that referenced this pull request Apr 26, 2024
* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Wrong learning rate scheduler training step count for examples with multi-gpu.
4 participants